[Fundamentals of Machine Learning and Neural Networks]
When comparing and contrasting the ReLU and sigmoid activation functions, which statement is true?
ReLU (Rectified Linear Unit) and sigmoid are activation functions used in neural networks. According to NVIDIA's deep learning documentation (e.g., cuDNN and TensorRT), ReLU, defined as f(x) = max(0, x), is computationally efficient because it involves simple thresholding, avoiding expensive exponential calculations required by sigmoid, f(x) = 1/(1 + e^(-x)). Sigmoid outputs values in the range
[0, 1], making it suitable for predicting probabilities in binary classification tasks. ReLU, with an unbounded positive range, is less suited for direct probability prediction but accelerates training by mitigating vanishing gradient issues. Option A is incorrect, as ReLU is non-linear (piecewise linear). Option B is false, as ReLU is more efficient and not inherently more accurate. Option C is wrong, as ReLU's range is
[0, ), not
[0, 1].
NVIDIA cuDNN Documentation: https://docs.nvidia.com/deeplearning/cudnn/developer-guide/index.html
Goodfellow, I., et al. (2016). 'Deep Learning.' MIT Press.
Tequila
7 months agoSalina
7 months agoErin
7 months agoNelida
7 months agoCornell
7 months agoFlo
8 months agoGregoria
8 months agoDylan
8 months agoThurman
8 months agoClarinda
8 months agoGearldine
9 months agoBeckie
9 months agoCorinne
9 months agoJudy
11 months agoMollie
9 months agoCaprice
11 months agoJeff
12 months agoErick
12 months agoDean
12 months agoJosue
10 months agoRachael
11 months agoIzetta
11 months agoPeggie
11 months agoSilva
12 months agoAndra
12 months agoOnita
1 year agoDana
1 year agoRyan
1 year agoKatheryn
12 months agoWilliam
1 year agoMagda
1 year ago